On the Convergence Rate of LoRA Gradient Descent

• URL: http://arxiv.org/abs/2512.18248v1
• Date: Sat, 20 Dec 2025 07:20:54 GMT
• Title: On the Convergence Rate of LoRA Gradient Descent
• Authors: Siqiao Mu, Diego Klabjan,
• Abstract summary: We present a non-asymptotic convergence analysis of the textitoriginal LoRA gradient descent algorithm.<n>We prove that LoRA gradient descent converges to a stationary point at rate $O(frac1log T)$, where $T$ is the number of iterations.
• Score: 22.183624306817563
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The low-rank adaptation (LoRA) algorithm for fine-tuning large models has grown popular in recent years due to its remarkable performance and low computational requirements. LoRA trains two ``adapter" matrices that form a low-rank representation of the model parameters, thereby massively reducing the number of parameters that need to be updated at every step. Although LoRA is simple, its convergence is poorly understood due to the lack of Lipschitz smoothness, a key condition for classic convergence analyses. As a result, current theoretical results only consider asymptotic behavior or assume strong boundedness conditions which artificially enforce Lipschitz smoothness. In this work, we provide for the first time a non-asymptotic convergence analysis of the \textit{original LoRA gradient descent} algorithm, which reflects widespread practice, without such assumptions. Our work relies on three key steps: i) reformulating the problem in terms of the outer product of the stacked adapter matrices, ii) a modified descent lemma for the ``Lipschitz-like" reparametrized function, and iii) controlling the step size. With this approach, we prove that LoRA gradient descent converges to a stationary point at rate $O(\frac{1}{\log T})$, where $T$ is the number of iterations.

Related papers

• Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation [58.288682735160585]
  Low-Rank Adaptation (LoRA) is a popular technique for finetuning models. LoRA often under performs when compared to full- parameter fine-tuning. We present a framework that rigorously analyzes the adaptation rates of LoRA methods.
  arXiv  Detail & Related papers  (2024-10-10T18:51:53Z)
• Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models [10.827800772359844]
  We study the computational limits of Low-Rank Adaptation (LoRA) for finetuning transformer-based models using fine-grained complexity theory.<n>Our key observation is that the existence of low-rank decompositions within the gradient computation of LoRA adaptation leads to possible algorithmic speedup.
  arXiv  Detail & Related papers  (2024-06-05T10:44:08Z)
• A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization [90.87444114491116]
  This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparametricized two-layer neural networks. We address (i) the convergence of the gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. Results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(alpha-1)$, measured in terms of the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-04-18T16:46:08Z)
• Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models [45.72323731094864]
  Low-Rank Adaptation (LoRA) emerges as a popular parameter-efficient fine-tuning (PEFT) method. In this work, we study the enhancement of LoRA training by introducing an $r times r$ preconditioner in each gradient step.
  arXiv  Detail & Related papers  (2024-02-04T05:05:43Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Smoothing ADMM for Sparse-Penalized Quantile Regression with Non-Convex Penalties [8.294148737585543]
  This paper investigates concave and clipped quantile regression in the presence of nonsecondary absolute and non-smooth convergence penalties. We introduce a novel-loop ADM algorithm with an increasing penalty multiplier, named SIAD, specifically for sparse regression.
  arXiv  Detail & Related papers  (2023-09-04T21:48:51Z)
• Max-affine regression via first-order methods [7.12511675782289]
  The max-affine model ubiquitously arises in applications in signal processing and statistics. We present a non-asymptotic convergence analysis of gradient descent (GD) and mini-batch gradient descent (SGD) for max-affine regression.
  arXiv  Detail & Related papers  (2023-08-15T23:46:44Z)
• Convergence of Adam Under Relaxed Assumptions [72.24779199744954]
  We show that Adam converges to $epsilon$-stationary points with $O(epsilon-4)$ gradient complexity under far more realistic conditions. We also propose a variance-reduced version of Adam with an accelerated gradient complexity of $O(epsilon-3)$.
  arXiv  Detail & Related papers  (2023-04-27T06:27:37Z)
• KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal [70.15267479220691]
  We consider and analyze the sample complexity of model reinforcement learning with a generative variance-free model. Our analysis shows that it is nearly minimax-optimal for finding an $varepsilon$-optimal policy when $varepsilon$ is sufficiently small.
  arXiv  Detail & Related papers  (2022-05-27T19:39:24Z)
• A Retrospective Approximation Approach for Smooth Stochastic Optimization [0.2867517731896504]
  Gradient (SG) is the defactorandom iterative technique to solve optimization (SO) problems with a smooth (non-fimation) objective $imation.
  arXiv  Detail & Related papers  (2021-03-07T16:29:36Z)
• Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems [120.21685755278509]
  In this work, we seek to balance the fact that attenuating step-size is required for exact convergence with the fact that constant step-size learns faster in time up to an error. Rather than fixing the minibatch the step-size at the outset, we propose to allow parameters to evolve adaptively.
  arXiv  Detail & Related papers  (2020-07-02T16:02:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.